Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4002
    Prev
    Next
    INDEX
    Explanations

    specific types of quilts and patchwork designs, as well as terms related to the crafting process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pitch
    -0.47
    losing
    -0.47
     pitch
    -0.47
     losing
    -0.47
    anen
    -0.44
     assisti
    -0.43
     kindred
    -0.43
    фициальный
    -0.43
    ʊ
    -0.42
     loss
    -0.41
    POSITIVE LOGITS
    DoubleQuotes
    0.78
     kasarigan
    0.75
    ulipas
    0.74
    endphp
    0.68
     dam
    0.67
    addContainerGap
    0.67
    IndentedString
    0.66
     propOrder
    0.66
     dams
    0.66
    出版年
    0.66
    Activations Density 3.034%

    No Known Activations